A Study of the Influence of Data Complexity and Similarity on Soft Biometrics Classification Performance in a Transfer Learning Scenario

Transfer learning is a paradigm that consists in training and testing classifiers with datasets drawn from distinct distributions. This technique allows to solve a particular problem using a model that was trained for another purpose. In the recent years, this practice has become very popular due to the increase of public available pre-trained models that can be fine-tuned to be applied in different scenarios. However, the relationship between the datasets used for training the model and the test data is usually not addressed, specially where the fine-tuning process is done only for the fully connected layers of a Convolutional Neural Network with pre-trained weights. This work presents a study regarding the relationship between the datasets used in a transfer learning process in terms of the performance achieved by models complexities and similarities. For this purpose, we fine-tune the final layer of Convolutional Neural Networks with pre-trained weights using diverse soft biometrics datasets. An evaluation of the performances of the models, when tested with datasets that are different from the one used for training the model, is presented. Complexity and similarity metrics are also used to perform the evaluation.

Download Full-text

What is in Balkan History? Spaces and Scales in the Tradition of Southeast-European Studies

Southeastern Europe ◽

10.1163/187633309x12563839996621 ◽

2010 ◽

Vol 34 (1) ◽

pp. 55-86 ◽

Cited By ~ 3

Author(s):

Diana Mishkova

Keyword(s):

Methodological Approach ◽

Theoretical Perspective ◽

The Other ◽

Southeastern Europe ◽

The Balkans ◽

Historical Reality ◽

Historical Times ◽

The One ◽

The Relationship ◽

Fine Tune

AbstractThis article takes a distance from the debate about 'symbolic geographies' and structural definitions of historical spaces as well as from surveying discrete disciplinary traditions or political agendas of regionalist scholarship in and on Southeastern Europe. Its purpose instead has been two-fold. On the one hand, to bring to light a preexistent but largely suppressed and un-reflected tradition of regionalist scholarship with the hope that this could help us fine tune the way we conceptualize, contemplate and evaluate regionalism as politics and transnationalism as a scholarly project. In epistemological terms, on the other hand, it proposes a theoretical perspective to regionalist scholarship involving rigorous engagement with the scales of observation, and scale shifts, in the interpretation of history. The hypothesis the article seeks to test maintains that the national and the (meso)regional perspectives to history chart differentiated 'spaces of experience' — i.e. the same occurrences are reported and judged in a different manner on the different scales — by way of displacing the valency of past processes, events, actors, and institutions and creating divergent temporalities — different national and regional historical times. Different objects (i.e. spaces) of enquiry are therefore coextensive with different temporal layers, each of which demands a different methodological approach. Drawing on texts of regional scholars, in which the historical reality of the Balkans/Southeastern Europe is articulated explicitly or implicitly, the article discusses also the relationship between different spaces and scales at the backdrop of the Braudelian and the microhistorical perspectives.

Download Full-text

FnnmOS-ELM: A Flexible Neural Network Mixed Online Sequential Elm

Applied Sciences ◽

10.3390/app9183772 ◽

2019 ◽

Vol 9 (18) ◽

pp. 3772

Author(s):

Xiali Li ◽

Shuai He ◽

Junzhi Yu ◽

Licheng Wu ◽

Zhao Yue

Keyword(s):

Neural Network ◽

Network Performance ◽

Classification Performance ◽

Feature Representation ◽

Mixed Structure ◽

Training Time ◽

Learning Speed ◽

Learning Machine ◽

Fully Connected ◽

The Relationship

The learning speed of online sequential extreme learning machine (OS-ELM) algorithms is much higher than that of convolutional neural networks (CNNs) or recurrent neural network (RNNs) on regression and simple classification datasets. However, the general feature extraction of OS-ELM makes it difficult to conveniently and effectively perform classification on some large and complex datasets, e.g., CIFAR. In this paper, we propose a flexible OS-ELM-mixed neural network, termed as fnnmOS-ELM. In this mixed structure, the OS-ELM can replace a part of fully connected layers in CNNs or RNNs. Our framework not only exploits the strong feature representation of CNNs or RNNs, but also performs at a fast speed in terms of classification. Additionally, it avoids the problem of long training time and large parameter size of CNNs or RNNs to some extent. Further, we propose a method for optimizing network performance by splicing OS-ELM after CNN or RNN structures. Iris, IMDb, CIFAR-10, and CIFAR-100 datasets are employed to verify the performance of the fnnmOS-ELM. The relationship between hyper-parameters and the performance of the fnnmOS-ELM is explored, which sheds light on the optimization of network performance. Finally, the experimental results demonstrate that the fnnmOS-ELM has a stronger feature representation and higher classification performance than contemporary methods.

Download Full-text

How Deeply to Fine-Tune a Convolutional Neural Network: A Case Study Using a Histopathology Dataset

Applied Sciences ◽

10.3390/app10103359 ◽

2020 ◽

Vol 10 (10) ◽

pp. 3359 ◽

Cited By ~ 2

Author(s):

Ibrahem Kandel ◽

Mauro Castelli

Keyword(s):

Image Classification ◽

Transfer Learning ◽

Medical Image ◽

Disease Diagnosis ◽

Fine Tuning ◽

Medical Image Classification ◽

Fine Tune ◽

Entire Network

Accurate classification of medical images is of great importance for correct disease diagnosis. The automation of medical image classification is of great necessity because it can provide a second opinion or even a better classification in case of a shortage of experienced medical staff. Convolutional neural networks (CNN) were introduced to improve the image classification domain by eliminating the need to manually select which features to use to classify images. Training CNN from scratch requires very large annotated datasets that are scarce in the medical field. Transfer learning of CNN weights from another large non-medical dataset can help overcome the problem of medical image scarcity. Transfer learning consists of fine-tuning CNN layers to suit the new dataset. The main questions when using transfer learning are how deeply to fine-tune the network and what difference in generalization that will make. In this paper, all of the experiments were done on two histopathology datasets using three state-of-the-art architectures to systematically study the effect of block-wise fine-tuning of CNN. Results show that fine-tuning the entire network is not always the best option; especially for shallow networks, alternatively fine-tuning the top blocks can save both time and computational power and produce more robust classifiers.

Download Full-text

Active Learning for Effectively Fine-Tuning Transfer Learning to Downstream Task

ACM Transactions on Intelligent Systems and Technology ◽

10.1145/3446343 ◽

2021 ◽

Vol 12 (2) ◽

pp. 1-24

Author(s):

Md Abul Bashar ◽

Richi Nayak

Keyword(s):

Active Learning ◽

Transfer Learning ◽

Language Processing ◽

State Of The Art ◽

Language Model ◽

Ensemble Classifier ◽

Classification Performance ◽

Fine Tuning ◽

Linguistic Features ◽

Better Than

Language model (LM) has become a common method of transfer learning in Natural Language Processing (NLP) tasks when working with small labeled datasets. An LM is pretrained using an easily available large unlabelled text corpus and is fine-tuned with the labelled data to apply to the target (i.e., downstream) task. As an LM is designed to capture the linguistic aspects of semantics, it can be biased to linguistic features. We argue that exposing an LM model during fine-tuning to instances that capture diverse semantic aspects (e.g., topical, linguistic, semantic relations) present in the dataset will improve its performance on the underlying task. We propose a Mixed Aspect Sampling (MAS) framework to sample instances that capture different semantic aspects of the dataset and use the ensemble classifier to improve the classification performance. Experimental results show that MAS performs better than random sampling as well as the state-of-the-art active learning models to abuse detection tasks where it is hard to collect the labelled data for building an accurate classifier.

Download Full-text

Unsupervised extractive multi-document summarization method based on transfer learning from BERT multi-task fine-tuning

Journal of Information Science ◽

10.1177/0165551521990616 ◽

2021 ◽

pp. 016555152199061

Author(s):

Salima Lamsiyah ◽

Abdelkader El Mahdaouy ◽

Saïd El Alaoui Ouatik ◽

Bernard Espinasse

Keyword(s):

Transfer Learning ◽

State Of The Art ◽

Representation Learning ◽

Fine Tuning ◽

Text Representation ◽

Document Summarization ◽

Semantic Relationships ◽

Benchmark Datasets ◽

Tuning Methods ◽

Fine Tune

Text representation is a fundamental cornerstone that impacts the effectiveness of several text summarization methods. Transfer learning using pre-trained word embedding models has shown promising results. However, most of these representations do not consider the order and the semantic relationships between words in a sentence, and thus they do not carry the meaning of a full sentence. To overcome this issue, the current study proposes an unsupervised method for extractive multi-document summarization based on transfer learning from BERT sentence embedding model. Moreover, to improve sentence representation learning, we fine-tune BERT model on supervised intermediate tasks from GLUE benchmark datasets using single-task and multi-task fine-tuning methods. Experiments are performed on the standard DUC’2002–2004 datasets. The obtained results show that our method has significantly outperformed several baseline methods and achieves a comparable and sometimes better performance than the recent state-of-the-art deep learning–based methods. Furthermore, the results show that fine-tuning BERT using multi-task learning has considerably improved the performance.

Download Full-text

Mapping Impervious Surfaces in Town–Rural Transition Belts Using China’s GF-2 Imagery and Object-Based Deep CNNs

Remote Sensing ◽

10.3390/rs11030280 ◽

2019 ◽

Vol 11 (3) ◽

pp. 280 ◽

Cited By ~ 7

Author(s):

Yongyong Fu ◽

Kunkun Liu ◽

Zhangquan Shen ◽

Jinsong Deng ◽

Muye Gan ◽

...

Keyword(s):

Transfer Learning ◽

Rural Areas ◽

State Of The Art ◽

Classification Performance ◽

Learning Technologies ◽

Fine Tuning ◽

Great Success ◽

Impervious Surfaces ◽

Convolutional Network ◽

Object Based

Impervious surfaces play an important role in urban planning and sustainable environmental management. High-spatial-resolution (HSR) images containing pure pixels have significant potential for the detailed delineation of land surfaces. However, due to high intraclass variability and low interclass distance, the mapping and monitoring of impervious surfaces in complex town–rural areas using HSR images remains a challenge. The fully convolutional network (FCN) model, a variant of convolution neural networks (CNNs), recently achieved state-of-the-art performance in HSR image classification applications. However, due to the inherent nature of FCN processing, it is challenging for an FCN to precisely capture the detailed information of classification targets. To solve this problem, we propose an object-based deep CNN framework that integrates object-based image analysis (OBIA) with deep CNNs to accurately extract and estimate impervious surfaces. Specifically, we also adopted two widely used transfer learning technologies to expedite the training of deep CNNs. Finally, we compare our approach with conventional OBIA classification and state-of-the-art FCN-based methods, such as FCN-8s and the U-Net methods. Both of these FCN-based methods are well designed for pixel-wise classification applications and have achieved great success. Our results show that the proposed approach effectively identified impervious surfaces, with 93.9% overall accuracy. Compared with the existing methods, i.e., OBIA, FCN-8s and U-Net methods, it shows that our method achieves obviously improvement in accuracy. Our findings also suggest that the classification performance of our proposed method is related to training strategy, indicating that significantly higher accuracy can be achieved through transfer learning by fine-tuning rather than feature extraction. Our approach for the automatic extraction and mapping of impervious surfaces also lays a solid foundation for intelligent monitoring and the management of land use and land cover.

Download Full-text

AdaFilter: Adaptive Filter Fine-Tuning for Deep Transfer Learning

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i04.5824 ◽

2020 ◽

Vol 34 (04) ◽

pp. 4060-4066

Author(s):

Yunhui Guo ◽

Yandong Li ◽

Liqiang Wang ◽

Tajana Rosing

Keyword(s):

Transfer Learning ◽

Deep Neural Networks ◽

Network Models ◽

Fine Tuning ◽

Public Image ◽

Classification Error ◽

Neural Network Models ◽

Learning Technique ◽

Task Transfer ◽

Fine Tune

There is an increasing number of pre-trained deep neural network models. However, it is still unclear how to effectively use these models for a new task. Transfer learning, which aims to transfer knowledge from source tasks to a target task, is an effective solution to this problem. Fine-tuning is a popular transfer learning technique for deep neural networks where a few rounds of training are applied to the parameters of a pre-trained model to adapt them to a new task. Despite its popularity, in this paper we show that fine-tuning suffers from several drawbacks. We propose an adaptive fine-tuning approach, called AdaFilter, which selects only a part of the convolutional filters in the pre-trained model to optimize on a per-example basis. We use a recurrent gated network to selectively fine-tune convolutional filters based on the activations of the previous layer. We experiment with 7 public image classification datasets and the results show that AdaFilter can reduce the average classification error of the standard fine-tuning by 2.54%.

Download Full-text

The Diagnosis of COVID-19 through X-ray Images via Transfer Learning and Fine-Tuned Dense Layer on Pipeline

Mekatronika ◽

10.15282/mekatronika.v3i2.7161 ◽

2021 ◽

Vol 3 (2) ◽

pp. 19-24

Author(s):

Amiir Haamzah Mohamed Ismail ◽

Mohd Azraai Mohd Razman ◽

Ismail Mohd Khairuddin ◽

Muhammad Amirul Abdullah ◽

Rabiu Muazu Musa ◽

...

Keyword(s):

Machine Learning ◽

Transfer Learning ◽

Screening Method ◽

Learning Technologies ◽

Fine Tuning ◽

Dense Layer ◽

X Ray ◽

Chest X Ray ◽

The Common ◽

Fully Connected

X-ray is used in medical treatment as a method to diagnose the human body internally from diseases. Nevertheless, the development in machine learning technologies for pattern recognition have allowed machine learning of diagnosing diseases from chest X-ray images. One such diseases that are able to be detected by using X-ray is the COVID-19 coronavirus. This research investigates the diagnosis of COVID-19 through X-ray images by using transfer learning and fine-tuning of the fully connected layer. Next, hyperparameters such as dropout, p, number of neurons, and activation functions are investigated on which combinations of these hyperparameters will yield the highest classification accuracy model. InceptionV3 which is one of the common neural network is used for feature extraction from chest X-ray images. Subsequently, the loss and accuracy graphs are used to find the pipeline which performs the best in classification task. The findings in this research will open new possibilities in screening method for COVID-19.

Download Full-text

The importance of transfer learning in seismic modeling and imaging

Geophysics ◽

10.1190/geo2019-0056.1 ◽

2019 ◽

Vol 84 (6) ◽

pp. A47-A52 ◽

Cited By ~ 8

Author(s):

Ali Siahkoohi ◽

Mathias Louboutin ◽

Felix J. Herrmann

Keyword(s):

Neural Network ◽

Transfer Learning ◽

Low Cost ◽

Fine Tuning ◽

Numerical Dispersion ◽

High Fidelity ◽

Velocity Models ◽

Current Survey ◽

Exploration Seismology ◽

Fine Tune

Accurate forward modeling is essential for solving inverse problems in exploration seismology. Unfortunately, it is often not possible to afford being physically or numerically accurate. To overcome this conundrum, we make use of raw and processed data from nearby surveys. We have used these data, consisting of shot records or velocity models, to pretrain a neural network to correct for the effects of, for instance, the free surface or numerical dispersion, both of which can be considered as proxies for incomplete or inaccurate physics. Given this pretrained neural network, we apply transfer learning to fine-tune this pretrained neural network so it performs well on its task of mapping low-cost, but low-fidelity, solutions to high-fidelity solutions for the current survey. As long as we can limit ourselves during fine-tuning to using only a small fraction of high-fidelity data, we gain processing the current survey while using information from nearby surveys. We examined this principle by removing surface-related multiples and ghosts from shot records and the effects of numerical dispersion from migrated images and wave simulations.

Download Full-text

Better Fine-Tuning via Instance Weighting for Text Classification

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v33i01.33017241 ◽

2019 ◽

Vol 33 ◽

pp. 7241-7248

Author(s):

Zhi Wang ◽

Wei Bi ◽

Yan Wang ◽

Xiaojiang Liu

Keyword(s):

Transfer Learning ◽

Text Classification ◽

Fine Tuning ◽

Model Parameters ◽

Great Success ◽

Target Domain ◽

Instance Weighting ◽

Training Stage ◽

Effective Transfer ◽

Fine Tune

Transfer learning for deep neural networks has achieved great success in many text classification applications. A simple yet effective transfer learning method is to fine-tune the pretrained model parameters. Previous fine-tuning works mainly focus on the pre-training stage and investigate how to pretrain a set of parameters that can help the target task most. In this paper, we propose an Instance Weighting based Finetuning (IW-Fit) method, which revises the fine-tuning stage to improve the final performance on the target domain. IW-Fit adjusts instance weights at each fine-tuning epoch dynamically to accomplish two goals: 1) identify and learn the specific knowledge of the target domain effectively; 2) well preserve the shared knowledge between the source and the target domains. The designed instance weighting metrics used in IW-Fit are model-agnostic, which are easy to implement for general DNN-based classifiers. Experimental results show that IW-Fit can consistently improve the classification accuracy on the target domain.

Download Full-text